Merge tag 'v5.8.5' into dev-5.8dev-5.8

This is the 5.8.5 stable release

Signed-off-by: Joel Stanley <joel@jms.id.au>

11 files changed, 51 insertions, 38 deletions

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index b12fbc857f94..5c41e13496a0 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -811,7 +811,8 @@ static int bnxt_re_handle_qp_async_event(struct creq_qp_event *qp_event,
 	struct ib_event event;
 	unsigned int flags;
 
-	if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+	if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR &&
+	    rdma_is_kernel_res(&qp->ib_qp.res)) {
 		flags = bnxt_re_lock_cqs(qp);
 		bnxt_qplib_add_flush_qp(&qp->qplib_qp);
 		bnxt_re_unlock_cqs(qp, flags);
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 962dc97a8ff2..1e4f4e525598 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -399,7 +399,6 @@ static int finish_mem_reg(struct c4iw_mr *mhp, u32 stag)
 	mmid = stag >> 8;
 	mhp->ibmr.rkey = mhp->ibmr.lkey = stag;
 	mhp->ibmr.length = mhp->attr.len;
-	mhp->ibmr.iova = mhp->attr.va_fbo;
 	mhp->ibmr.page_size = 1U << (mhp->attr.page_size + 12);
 	pr_debug("mmid 0x%x mhp %p\n", mmid, mhp);
 	return xa_insert_irq(&mhp->rhp->mrs, mmid, mhp, GFP_KERNEL);
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index facff133139a..3ba299cfd0b5 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -3215,6 +3215,7 @@ bool hfi1_tid_rdma_wqe_interlock(struct rvt_qp *qp, struct rvt_swqe *wqe)
 	case IB_WR_ATOMIC_CMP_AND_SWP:
 	case IB_WR_ATOMIC_FETCH_AND_ADD:
 	case IB_WR_RDMA_WRITE:
+	case IB_WR_RDMA_WRITE_WITH_IMM:
 		switch (prev->wr.opcode) {
 		case IB_WR_TID_RDMA_WRITE:
 			req = wqe_to_tid_req(prev);
diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 479fa557993e..c69453a62767 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -66,8 +66,6 @@
 #define HNS_ROCE_CQE_WCMD_EMPTY_BIT		0x2
 #define HNS_ROCE_MIN_CQE_CNT			16
 
-#define HNS_ROCE_RESERVED_SGE			1
-
 #define HNS_ROCE_MAX_IRQ_NUM			128
 
 #define HNS_ROCE_SGE_IN_WQE			2
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 0618ced45bf8..38a48ab3e1d0 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -629,7 +629,7 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 
 		wqe_idx = (hr_qp->rq.head + nreq) & (hr_qp->rq.wqe_cnt - 1);
 
-		if (unlikely(wr->num_sge >= hr_qp->rq.max_gs)) {
+		if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) {
 			ibdev_err(ibdev, "rq:num_sge=%d >= qp->sq.max_gs=%d\n",
 				  wr->num_sge, hr_qp->rq.max_gs);
 			ret = -EINVAL;
@@ -649,7 +649,6 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 		if (wr->num_sge < hr_qp->rq.max_gs) {
 			dseg->lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY);
 			dseg->addr = 0;
-			dseg->len = cpu_to_le32(HNS_ROCE_INVALID_SGE_LENGTH);
 		}
 
 		/* rq support inline data */
@@ -783,8 +782,8 @@ static int hns_roce_v2_post_srq_recv(struct ib_srq *ibsrq,
 		}
 
 		if (wr->num_sge < srq->max_gs) {
-			dseg[i].len = cpu_to_le32(HNS_ROCE_INVALID_SGE_LENGTH);
-			dseg[i].lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY);
+			dseg[i].len = 0;
+			dseg[i].lkey = cpu_to_le32(0x100);
 			dseg[i].addr = 0;
 		}
 
@@ -3053,6 +3052,7 @@ static void get_cqe_status(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp,
 		  IB_WC_RETRY_EXC_ERR },
 		{ HNS_ROCE_CQE_V2_RNR_RETRY_EXC_ERR, IB_WC_RNR_RETRY_EXC_ERR },
 		{ HNS_ROCE_CQE_V2_REMOTE_ABORT_ERR, IB_WC_REM_ABORT_ERR },
+		{ HNS_ROCE_CQE_V2_GENERAL_ERR, IB_WC_GENERAL_ERR}
 	};
 
 	u32 cqe_status = roce_get_field(cqe->byte_4, V2_CQE_BYTE_4_STATUS_M,
@@ -3075,6 +3075,14 @@ static void get_cqe_status(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp,
 		       sizeof(*cqe), false);
 
 	/*
+	 * For hns ROCEE, GENERAL_ERR is an error type that is not defined in
+	 * the standard protocol, the driver must ignore it and needn't to set
+	 * the QP to an error state.
+	 */
+	if (cqe_status == HNS_ROCE_CQE_V2_GENERAL_ERR)
+		return;
+
+	/*
 	 * Hip08 hardware cannot flush the WQEs in SQ/RQ if the QP state gets
 	 * into errored mode. Hence, as a workaround to this hardware
 	 * limitation, driver needs to assist in flushing. But the flushing
@@ -4301,7 +4309,9 @@ static bool check_qp_state(enum ib_qp_state cur_state,
 		[IB_QPS_RTR] = { [IB_QPS_RESET] = true,
 				 [IB_QPS_RTS] = true,
 				 [IB_QPS_ERR] = true },
-		[IB_QPS_RTS] = { [IB_QPS_RESET] = true, [IB_QPS_ERR] = true },
+		[IB_QPS_RTS] = { [IB_QPS_RESET] = true,
+				 [IB_QPS_RTS] = true,
+				 [IB_QPS_ERR] = true },
 		[IB_QPS_SQD] = {},
 		[IB_QPS_SQE] = {},
 		[IB_QPS_ERR] = { [IB_QPS_RESET] = true, [IB_QPS_ERR] = true }
@@ -5087,7 +5097,7 @@ static int hns_roce_v2_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr)
 
 	attr->srq_limit = limit_wl;
 	attr->max_wr = srq->wqe_cnt - 1;
-	attr->max_sge = srq->max_gs - HNS_ROCE_RESERVED_SGE;
+	attr->max_sge = srq->max_gs;
 
 out:
 	hns_roce_free_cmd_mailbox(hr_dev, mailbox);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index e176b0aaa4ac..4f840997c6c7 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -92,9 +92,7 @@
 #define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ		PAGE_SIZE
 #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED		0xFFFFF000
 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM		2
-#define HNS_ROCE_INVALID_LKEY			0x0
-#define HNS_ROCE_INVALID_SGE_LENGTH		0x80000000
-
+#define HNS_ROCE_INVALID_LKEY			0x100
 #define HNS_ROCE_CMQ_TX_TIMEOUT			30000
 #define HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE	2
 #define HNS_ROCE_V2_RSV_QPS			8
@@ -230,6 +228,7 @@ enum {
 	HNS_ROCE_CQE_V2_TRANSPORT_RETRY_EXC_ERR		= 0x15,
 	HNS_ROCE_CQE_V2_RNR_RETRY_EXC_ERR		= 0x16,
 	HNS_ROCE_CQE_V2_REMOTE_ABORT_ERR		= 0x22,
+	HNS_ROCE_CQE_V2_GENERAL_ERR			= 0x23,
 
 	HNS_ROCE_V2_CQE_STATUS_MASK			= 0xff,
 };
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index a0a47bd66975..4edea397b6b8 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -386,8 +386,7 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap,
 		return -EINVAL;
 	}
 
-	hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge) +
-					      HNS_ROCE_RESERVED_SGE);
+	hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge));
 
 	if (hr_dev->caps.max_rq_sg <= HNS_ROCE_SGE_IN_WQE)
 		hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz);
@@ -402,7 +401,7 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap,
 		hr_qp->rq_inl_buf.wqe_cnt = 0;
 
 	cap->max_recv_wr = cnt;
-	cap->max_recv_sge = hr_qp->rq.max_gs - HNS_ROCE_RESERVED_SGE;
+	cap->max_recv_sge = hr_qp->rq.max_gs;
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c
index f40a000e94ee..b9e2dbd372b6 100644
--- a/drivers/infiniband/hw/hns/hns_roce_srq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_srq.c
@@ -297,7 +297,7 @@ int hns_roce_create_srq(struct ib_srq *ib_srq,
 	spin_lock_init(&srq->lock);
 
 	srq->wqe_cnt = roundup_pow_of_two(init_attr->attr.max_wr + 1);
-	srq->max_gs = init_attr->attr.max_sge + HNS_ROCE_RESERVED_SGE;
+	srq->max_gs = init_attr->attr.max_sge;
 
 	if (udata) {
 		ret = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 7e0b205c05eb..d7c78f841d2f 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -439,7 +439,6 @@ struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 
 	mr->ibmr.rkey = mr->ibmr.lkey = mr->mmr.key;
 	mr->ibmr.length = length;
-	mr->ibmr.iova = virt_addr;
 	mr->ibmr.page_size = 1U << shift;
 
 	return &mr->ibmr;
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index fdf90ecb2699..460292179b32 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -235,6 +235,7 @@ struct qedr_ucontext {
 	u32 dpi_size;
 	u16 dpi;
 	bool db_rec;
+	u8 edpm_mode;
 };
 
 union db_prod32 {
@@ -344,10 +345,10 @@ struct qedr_srq_hwq_info {
 	u32 wqe_prod;
 	u32 sge_prod;
 	u32 wr_prod_cnt;
-	u32 wr_cons_cnt;
+	atomic_t wr_cons_cnt;
 	u32 num_elems;
 
-	u32 *virt_prod_pair_addr;
+	struct rdma_srq_producers *virt_prod_pair_addr;
 	dma_addr_t phy_prod_pair_addr;
 };
 
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 9b9e80266367..1a7f1f805be3 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -275,7 +275,8 @@ int qedr_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata)
 			DP_ERR(dev, "Problem copying data from user space\n");
 			return -EFAULT;
 		}
-
+		ctx->edpm_mode = !!(ureq.context_flags &
+				    QEDR_ALLOC_UCTX_EDPM_MODE);
 		ctx->db_rec = !!(ureq.context_flags & QEDR_ALLOC_UCTX_DB_REC);
 	}
 
@@ -316,11 +317,15 @@ int qedr_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata)
 		uresp.dpm_flags = QEDR_DPM_TYPE_IWARP_LEGACY;
 	else
 		uresp.dpm_flags = QEDR_DPM_TYPE_ROCE_ENHANCED |
-				  QEDR_DPM_TYPE_ROCE_LEGACY;
+				  QEDR_DPM_TYPE_ROCE_LEGACY |
+				  QEDR_DPM_TYPE_ROCE_EDPM_MODE;
 
-	uresp.dpm_flags |= QEDR_DPM_SIZES_SET;
-	uresp.ldpm_limit_size = QEDR_LDPM_MAX_SIZE;
-	uresp.edpm_trans_size = QEDR_EDPM_TRANS_SIZE;
+	if (ureq.context_flags & QEDR_SUPPORT_DPM_SIZES) {
+		uresp.dpm_flags |= QEDR_DPM_SIZES_SET;
+		uresp.ldpm_limit_size = QEDR_LDPM_MAX_SIZE;
+		uresp.edpm_trans_size = QEDR_EDPM_TRANS_SIZE;
+		uresp.edpm_limit_size = QEDR_EDPM_MAX_SIZE;
+	}
 
 	uresp.wids_enabled = 1;
 	uresp.wid_count = oparams.wid_count;
@@ -1750,7 +1755,7 @@ static int qedr_create_user_qp(struct qedr_dev *dev,
 	struct qed_rdma_create_qp_out_params out_params;
 	struct qedr_pd *pd = get_qedr_pd(ibpd);
 	struct qedr_create_qp_uresp uresp;
-	struct qedr_ucontext *ctx = NULL;
+	struct qedr_ucontext *ctx = pd ? pd->uctx : NULL;
 	struct qedr_create_qp_ureq ureq;
 	int alloc_and_init = rdma_protocol_roce(&dev->ibdev, 1);
 	int rc = -EINVAL;
@@ -1788,6 +1793,9 @@ static int qedr_create_user_qp(struct qedr_dev *dev,
 		in_params.rq_pbl_ptr = qp->urq.pbl_tbl->pa;
 	}
 
+	if (ctx)
+		SET_FIELD(in_params.flags, QED_ROCE_EDPM_MODE, ctx->edpm_mode);
+
 	qp->qed_qp = dev->ops->rdma_create_qp(dev->rdma_ctx,
 					      &in_params, &out_params);
 
@@ -3686,7 +3694,7 @@ static u32 qedr_srq_elem_left(struct qedr_srq_hwq_info *hw_srq)
 	 * count and consumer count and subtract it from max
 	 * work request supported so that we get elements left.
 	 */
-	used = hw_srq->wr_prod_cnt - hw_srq->wr_cons_cnt;
+	used = hw_srq->wr_prod_cnt - (u32)atomic_read(&hw_srq->wr_cons_cnt);
 
 	return hw_srq->max_wr - used;
 }
@@ -3701,7 +3709,6 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 	unsigned long flags;
 	int status = 0;
 	u32 num_sge;
-	u32 offset;
 
 	spin_lock_irqsave(&srq->lock, flags);
 
@@ -3714,7 +3721,8 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 		if (!qedr_srq_elem_left(hw_srq) ||
 		    wr->num_sge > srq->hw_srq.max_sges) {
 			DP_ERR(dev, "Can't post WR  (%d,%d) || (%d > %d)\n",
-			       hw_srq->wr_prod_cnt, hw_srq->wr_cons_cnt,
+			       hw_srq->wr_prod_cnt,
+			       atomic_read(&hw_srq->wr_cons_cnt),
 			       wr->num_sge, srq->hw_srq.max_sges);
 			status = -ENOMEM;
 			*bad_wr = wr;
@@ -3748,22 +3756,20 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 			hw_srq->sge_prod++;
 		}
 
-		/* Flush WQE and SGE information before
+		/* Update WQE and SGE information before
 		 * updating producer.
 		 */
-		wmb();
+		dma_wmb();
 
 		/* SRQ producer is 8 bytes. Need to update SGE producer index
 		 * in first 4 bytes and need to update WQE producer in
 		 * next 4 bytes.
 		 */
-		*srq->hw_srq.virt_prod_pair_addr = hw_srq->sge_prod;
-		offset = offsetof(struct rdma_srq_producers, wqe_prod);
-		*((u8 *)srq->hw_srq.virt_prod_pair_addr + offset) =
-			hw_srq->wqe_prod;
+		srq->hw_srq.virt_prod_pair_addr->sge_prod = hw_srq->sge_prod;
+		/* Make sure sge producer is updated first */
+		dma_wmb();
+		srq->hw_srq.virt_prod_pair_addr->wqe_prod = hw_srq->wqe_prod;
 
-		/* Flush producer after updating it. */
-		wmb();
 		wr = wr->next;
 	}
 
@@ -4182,7 +4188,7 @@ static int process_resp_one_srq(struct qedr_dev *dev, struct qedr_qp *qp,
 	} else {
 		__process_resp_one(dev, qp, cq, wc, resp, wr_id);
 	}
-	srq->hw_srq.wr_cons_cnt++;
+	atomic_inc(&srq->hw_srq.wr_cons_cnt);
 
 	return 1;
 }